US20100014774A1 - Methods and Systems for Content-Boundary Detection - Google Patents
Methods and Systems for Content-Boundary Detection Download PDFInfo
- Publication number
- US20100014774A1 US20100014774A1 US12/175,386 US17538608A US2010014774A1 US 20100014774 A1 US20100014774 A1 US 20100014774A1 US 17538608 A US17538608 A US 17538608A US 2010014774 A1 US2010014774 A1 US 2010014774A1
- Authority
- US
- United States
- Prior art keywords
- tile
- coordinate
- projection
- histogram
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
Definitions
- Embodiments of the present invention comprise methods and systems for automatically determining image-content boundaries.
- a digital page also considered a digital image, digital document and image.
- exemplary applications in which this may be useful include applications in which the page content may be repositioned on a different size page than the original, applications in which the page content may be composited with additional material and other document layout applications.
- Some embodiments of the present invention comprise methods and systems for determining content boundaries in a digital image.
- an edge detector based on local gradient computation may be used to generate a gradient field which may thresholded by magnitude to retain strong edges.
- the resulting localized edge positions may be projected onto a first direction and a second direction, which may be normal to the first direction, to form two projection histograms.
- the first direction may be related to a skew vector which describes the skew of the image content relative to the image axes.
- the projection histograms may be analyzed to determine the boundaries of the image content.
- the corners of a cropping rectangle may be computed, wherein the cropping rectangle may contain the desired content from the image.
- the digital image may be cropped according to the content boundaries.
- the digital image may be simultaneously cropped and corrected for skew.
- FIG. 1 is a chart showing exemplary embodiments of the present invention comprising extracting edges from an image, forming projection histograms from the edge maps and determining content boundaries from the projection histograms;
- FIG. 2 is a picture depicting exemplary projection histograms
- FIG. 3 is a picture depicting skewed image content
- FIG. 4 is a chart showing exemplary embodiments of the present invention comprising forming a low-resolution representation of an input image prior to determining content boundaries;
- FIG. 5 is a chart showing exemplary embodiments of the present invention comprising smoothing a low-resolution representation of an input image prior to determining content boundaries;
- FIG. 6 is a chart showing exemplary embodiments of the present invention comprising smoothing an input image prior to determining content boundaries
- FIG. 7 is a chart showing exemplary embodiments of the present invention comprising partitioning an image into non-overlapping blocks and determining block content boundaries
- FIG. 8 is a chart showing exemplary embodiments of the present invention comprising partitioning an image into overlapping blocks and determining block content boundaries.
- a digital page also considered a digital image, digital document and image.
- exemplary applications in which this may be useful include applications in which the page content may be repositioned on a different size page than the original, applications in which the page content may be composited with additional material and other document layout applications. It may be desirable to perform cropping automatically without user interaction. It also may be desirable to perform cropping on a digital page comprising an arbitrarily shaped content region, and it may be desirable to perform cropping when the digital page content is skewed with respect to the orthogonal image axes.
- Some embodiments of the present invention described in relation to FIG. 1 comprise methods and systems for automatically determining the content boundaries in a digital page.
- the location of the edges in the digital page may be extracted 4 , also considered detected or determined, thereby producing an edge mask, or other representation, indicating locations of large gradient magnitude in the digital page.
- the edge mask may be projected on a skew vector and the skew vector normal vector to form 6 two projection histograms.
- the content boundaries may be detected 8 , also considered determined, from the two projection histograms.
- edge-location determination 4 may comprise computing a gradient magnitude at each pixel in the digital page and thresholding the gradient magnitude results to form an edge mask.
- the gradient field in the x-direction, which may be denoted G x and the gradient field in the y-direction, which may be denoted G y , may be determined independently, and the gradient magnitude, which may be denoted G, may be determined according to:
- the digital page which may be denoted I, may be independently convolved with two edge kernels to determine the gradient fields in the x-direction and the y-direction.
- the edge kernels may comprise Sobel operators, and the gradient fields may be determined according to:
- edge detection may comprise other edge operators and methods known in the art, for example, a Canny edge detector, a Prewitt edge detector, a Roberts Cross kernel and a Hough transform.
- the gradient magnitude, G may be thresholded to form a binary image, also considered edge map, which may be denoted G′.
- the binary image, G′ may be set equal to one of the binary values when a first condition is satisfied and may be set to the other of the binary values when the first condition is not satisfied.
- the binary image, G′ may be determined according to:
- G ′ ⁇ ( i , j ) ⁇ 1 , G ⁇ ( i , j ) > ⁇ 0 , G ⁇ ( i , j ) ⁇ ⁇ ,
- ⁇ denotes an adaptive threshold based on the content of the image and (i, j) denotes a location in the gradient-magnitude image, G.
- the adaptive threshold, ⁇ may be determined according to:
- w is the width of and h is the height of the gradient-magnitude image, G, respectively
- p is a parameter which may control the rejection of the weakest p percentage of edges.
- the value of p may be set to 95.
- p may be set in the range of 93 to 97.
- Two projection histograms may be formed 6 by projecting the edge map, G′, onto a skew vector and a vector normal to the skew vector.
- Two exemplary projection histograms 10 , 11 are shown in FIG. 2 .
- the horizontal axis 12 , 13 of each histogram 10 , 11 indicates a coordinate in the direction of the axis, and the vertical axis 14 , 15 of each histogram 10 , 11 indicates a pixel count.
- the content boundaries in the directions of the skew vector and the skew vector normal may be determined 8 by the first and last histogram bins which contain pixel counts. For the exemplary histograms 10 , 11 shown in FIG. 2 these bins are indicated 16 , 17 , 18 , 19 .
- FIG. 3 shows an exemplary image 20 comprising a page region 22 which is skewed relative to the image axes.
- the skew vector 24 and the normal to the skew vector 26 are shown for an exemplary skew angle 28 .
- the skew vector 24 and the normal to the skew vector 26 are shown relative to an origin 30 which may be the same origin of the image coordinate system.
- the locations of the first and last histogram bins which contain pixel counts in the projection histogram associated with the skew vector 26 are labeled A 31 and B 32 .
- the locations of the first and last histogram bins which contain pixel counts in the projection histogram associated with the normal to the skew vector 26 are labeled C 33 and D 34 .
- a 31 may correspond to the location in the top histogram 10 of the first bin 16 from the origin which has a non-zero pixel count.
- B 32 may correspond to the location in the top histogram 10 of the last bin 18 from the origin which has a non-zero pixel count.
- C 33 may correspond to the location in the bottom histogram 11 of the first bin 17 from the origin which has a non-zero pixel count.
- D 34 may correspond to the location in the bottom histogram 11 of the last bin 19 from the origin which has a non-zero pixel count.
- the content boundaries may be described by the corners of a bounding rectangle. These corners may be denoted in relation to the locations determined from the projection histograms. Denoting the location of the first and last histogram bins with non-zero count in the projection histogram associated with the skew vector as left and right, respectively, and the location of the first and last histogram bins with non-zero count in the projection histogram associated with the skew vector normal as bottom and top, respectively, then the corners of the bounding rectangle may be given according to:
- bottom-left corner is (left, bottom) in the skewed coordinate system
- bottom-right corner is (right, bottom) in the skewed coordinate system
- top-left corner is (left, top) in the skewed coordinate system
- top-right corner is (right, top) in the skewed coordinate system.
- a low-resolution representation of an image may be derived 42 prior to determining 44 edge locations in the low-resolution representation.
- Projection histograms may be formed 46 from the edge map, and the content boundaries may be detected 48 using the projection histograms.
- the low-resolution representation may be derived 42 through sub-sampling and down-sampling techniques known in the art.
- the low-resolution representation of the input image may be a 75 dots-per-inch image.
- a low-resolution representation of an image may be derived 50 , and the low-resolution representation of the image may be smoothed 52 prior to determining 54 edge locations in the low-resolution representation.
- Projection histograms may be formed 56 from the edge map, and the content boundaries may be detected 58 using the projection histograms.
- the smoothed version of the low-resolution representation may be derived 52 by smoothing the low-resolution representation of the input image using a 3 ⁇ 3 Gaussian filter.
- smoothing may comprise Gaussian filters of other size, smoothing filters of other types and other smoothing techniques known in the art.
- an input image may be smoothed 62 prior to determining 64 edge locations in the smoothed image.
- Projection histograms may be formed 66 from the edge map, and the content boundaries may be detected 68 using the projection histograms.
- the smoothed version of the input image may be derived 62 by smoothing the input image using a 3 ⁇ 3 Gaussian filter.
- smoothing may comprise Gaussian filters of other size, smoothing filters of other types and other smoothing techniques known in the art.
- an image may be partitioned 72 into non-overlapping blocks.
- the block content boundaries may be determined 74 according to embodiments of the present invention described above.
- the block boundaries may be combined 76 to generate the content boundary for the image.
- the content boundaries, which may be designated by the bounding rectangle corners and denoted R, for the image may be determined 76 from the block boundaries according to:
- determination 74 of the block content boundaries may be performed in parallel by a plurality of processors. In alternative embodiments, the determination 74 of the block content boundaries may be performed serially.
- an image may be partitioned 82 into overlapping blocks.
- the block content boundaries may be determined 84 according to embodiments of the present invention described above.
- the block boundaries may be combined 86 to generate the content boundary for the image.
- the content boundaries, which may be designated by the bounding rectangle corners and denoted R, for the image may be determined 86 from the block boundaries according to:
- determination 84 of the block content boundaries may be performed in parallel by a plurality of processors. In alternative embodiments, the determination 84 of the block content boundaries may be performed serially.
- the input image may be a color image. In alternative embodiments of the present invention, the input image may be a gray-scale image. In still alternative embodiments of the present invention, the input image may be a binary image.
- the input image may be a luminance image corresponding to a color image.
- the input image may be a binary image corresponding to a color image.
- the input image may be a binary image corresponding to a gray-scale image.
- an image may be cropped according to the determined content boundaries.
- an image may be simultaneously cropped according to the determined content boundaries and skew corrected.
Abstract
Description
- Embodiments of the present invention comprise methods and systems for automatically determining image-content boundaries.
- It may be desirable to crop off extraneous portions of a digital page, also considered a digital image, digital document and image. In particular, in may be desirable to retain the content of the digital page while eliminating extraneous page margins. Exemplary applications in which this may be useful include applications in which the page content may be repositioned on a different size page than the original, applications in which the page content may be composited with additional material and other document layout applications. It may be desirable to perform cropping automatically without user interaction. It also may be desirable to perform cropping on a digital page comprising an arbitrarily shaped content region, and it may be desirable to perform cropping when the digital page content is skewed with respect to the orthogonal image axes. Methods and systems for automatically determining image-content boundaries, therefore, may be desirable.
- Some embodiments of the present invention comprise methods and systems for determining content boundaries in a digital image. In some embodiments of the present invention, an edge detector based on local gradient computation may be used to generate a gradient field which may thresholded by magnitude to retain strong edges. The resulting localized edge positions may be projected onto a first direction and a second direction, which may be normal to the first direction, to form two projection histograms. In some embodiments of the present invention, the first direction may be related to a skew vector which describes the skew of the image content relative to the image axes. The projection histograms may be analyzed to determine the boundaries of the image content. In some embodiments of the present invention, the corners of a cropping rectangle may be computed, wherein the cropping rectangle may contain the desired content from the image. In some embodiments of the present invention, the digital image may be cropped according to the content boundaries. In some embodiments of the present invention, the digital image may be simultaneously cropped and corrected for skew.
- The foregoing and other objectives, features, and advantages of the invention will be more readily understood upon consideration of the following detailed description of the invention taken in conjunction with the accompanying drawings.
-
FIG. 1 is a chart showing exemplary embodiments of the present invention comprising extracting edges from an image, forming projection histograms from the edge maps and determining content boundaries from the projection histograms; -
FIG. 2 is a picture depicting exemplary projection histograms; -
FIG. 3 is a picture depicting skewed image content; -
FIG. 4 is a chart showing exemplary embodiments of the present invention comprising forming a low-resolution representation of an input image prior to determining content boundaries; -
FIG. 5 is a chart showing exemplary embodiments of the present invention comprising smoothing a low-resolution representation of an input image prior to determining content boundaries; -
FIG. 6 is a chart showing exemplary embodiments of the present invention comprising smoothing an input image prior to determining content boundaries; -
FIG. 7 is a chart showing exemplary embodiments of the present invention comprising partitioning an image into non-overlapping blocks and determining block content boundaries; and -
FIG. 8 is a chart showing exemplary embodiments of the present invention comprising partitioning an image into overlapping blocks and determining block content boundaries. - Embodiments of the present invention will be best understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The figures listed above are expressly incorporated as part of this detailed description.
- It will be readily understood that the components of the present invention, as generally described and illustrated in the figures herein, could be arranged and designed in a wide variety of different configurations. Thus, the following more detailed description of the embodiments of the methods and systems of the present invention is not intended to limit the scope of the invention but it is merely representative of the presently preferred embodiments of the invention.
- Elements of embodiments of the present invention may be embodied in hardware, firmware and/or software. While exemplary embodiments revealed herein may only describe one of these forms, it is to be understood that one skilled in the art would be able to effectuate these elements in any of these forms while resting within the scope of the present invention.
- It may be desirable to crop off extraneous portions of a digital page, also considered a digital image, digital document and image. In particular, in may be desirable to retain the content of the digital page while eliminating extraneous page margins. Exemplary applications in which this may be useful include applications in which the page content may be repositioned on a different size page than the original, applications in which the page content may be composited with additional material and other document layout applications. It may be desirable to perform cropping automatically without user interaction. It also may be desirable to perform cropping on a digital page comprising an arbitrarily shaped content region, and it may be desirable to perform cropping when the digital page content is skewed with respect to the orthogonal image axes.
- Some embodiments of the present invention described in relation to
FIG. 1 comprise methods and systems for automatically determining the content boundaries in a digital page. In these embodiments, the location of the edges in the digital page may be extracted 4, also considered detected or determined, thereby producing an edge mask, or other representation, indicating locations of large gradient magnitude in the digital page. The edge mask may be projected on a skew vector and the skew vector normal vector to form 6 two projection histograms. The content boundaries may be detected 8, also considered determined, from the two projection histograms. - In some embodiments of the present invention described in relation to
FIG. 1 , edge-location determination 4 may comprise computing a gradient magnitude at each pixel in the digital page and thresholding the gradient magnitude results to form an edge mask. In some embodiments of the present invention, the gradient field in the x-direction, which may be denoted Gx, and the gradient field in the y-direction, which may be denoted Gy, may be determined independently, and the gradient magnitude, which may be denoted G, may be determined according to: -
G=∥∇∥ 1 =|G x |+G y|, - where |.| denotes absolute value.
- In some embodiments of the present invention, the digital page, which may be denoted I, may be independently convolved with two edge kernels to determine the gradient fields in the x-direction and the y-direction. In some embodiments the edge kernels may comprise Sobel operators, and the gradient fields may be determined according to:
-
- In alternative embodiments, edge detection may comprise other edge operators and methods known in the art, for example, a Canny edge detector, a Prewitt edge detector, a Roberts Cross kernel and a Hough transform.
- In some embodiments of the present invention, the gradient magnitude, G, may be thresholded to form a binary image, also considered edge map, which may be denoted G′. In these embodiments, the binary image, G′, may be set equal to one of the binary values when a first condition is satisfied and may be set to the other of the binary values when the first condition is not satisfied. In some embodiments of the present invention, the binary image, G′, may be determined according to:
-
- where θ denotes an adaptive threshold based on the content of the image and (i, j) denotes a location in the gradient-magnitude image, G.
- In some embodiments of the present invention, the adaptive threshold, θ, may be determined according to:
-
- in which w is the width of and h is the height of the gradient-magnitude image, G, respectively, and p is a parameter which may control the rejection of the weakest p percentage of edges. In some embodiments, the value of p may be set to 95. In alternative embodiments, p may be set in the range of 93 to 97.
- Two projection histograms may be formed 6 by projecting the edge map, G′, onto a skew vector and a vector normal to the skew vector. Two
exemplary projection histograms FIG. 2 . Thehorizontal axis histogram vertical axis histogram exemplary histograms FIG. 2 these bins are indicated 16, 17, 18, 19. - Embodiments of the present invention may be further understood in relation to
FIG. 3 .FIG. 3 shows anexemplary image 20 comprising apage region 22 which is skewed relative to the image axes. Theskew vector 24 and the normal to theskew vector 26 are shown for anexemplary skew angle 28. Theskew vector 24 and the normal to theskew vector 26 are shown relative to anorigin 30 which may be the same origin of the image coordinate system. The locations of the first and last histogram bins which contain pixel counts in the projection histogram associated with theskew vector 26 are labeled A 31 andB 32. The locations of the first and last histogram bins which contain pixel counts in the projection histogram associated with the normal to theskew vector 26 are labeledC 33 andD 34. In relation to theexemplary histograms FIG. 2 , assuming that thetop histogram 10 corresponds to the projection histogram associated with theskew vector 24 and thebottom histogram 11 corresponds to the projection histogram associated with the normal to theskew vector 26, then A 31 may correspond to the location in thetop histogram 10 of thefirst bin 16 from the origin which has a non-zero pixel count.B 32 may correspond to the location in thetop histogram 10 of thelast bin 18 from the origin which has a non-zero pixel count.C 33 may correspond to the location in thebottom histogram 11 of thefirst bin 17 from the origin which has a non-zero pixel count.D 34 may correspond to the location in thebottom histogram 11 of thelast bin 19 from the origin which has a non-zero pixel count. - In some embodiments of the present invention, the content boundaries may be described by the corners of a bounding rectangle. These corners may be denoted in relation to the locations determined from the projection histograms. Denoting the location of the first and last histogram bins with non-zero count in the projection histogram associated with the skew vector as left and right, respectively, and the location of the first and last histogram bins with non-zero count in the projection histogram associated with the skew vector normal as bottom and top, respectively, then the corners of the bounding rectangle may be given according to:
- bottom-left corner is (left, bottom) in the skewed coordinate system,
- bottom-right corner is (right, bottom) in the skewed coordinate system,
- top-left corner is (left, top) in the skewed coordinate system and
- top-right corner is (right, top) in the skewed coordinate system.
- Some embodiments of the present invention may be described in relation to
FIG. 4 . In these embodiments, a low-resolution representation of an image may be derived 42 prior to determining 44 edge locations in the low-resolution representation. Projection histograms may be formed 46 from the edge map, and the content boundaries may be detected 48 using the projection histograms. In some embodiments of the present invention, the low-resolution representation may be derived 42 through sub-sampling and down-sampling techniques known in the art. In some embodiments of the present invention, the low-resolution representation of the input image may be a 75 dots-per-inch image. - Some embodiments of the present invention may be described in relation to
FIG. 5 . In these embodiments, a low-resolution representation of an image may be derived 50, and the low-resolution representation of the image may be smoothed 52 prior to determining 54 edge locations in the low-resolution representation. Projection histograms may be formed 56 from the edge map, and the content boundaries may be detected 58 using the projection histograms. In some embodiments of the present invention, the smoothed version of the low-resolution representation may be derived 52 by smoothing the low-resolution representation of the input image using a 3×3 Gaussian filter. In alternative embodiments, smoothing may comprise Gaussian filters of other size, smoothing filters of other types and other smoothing techniques known in the art. - Some embodiments of the present invention may be described in relation to
FIG. 6 . In these embodiments, an input image may be smoothed 62 prior to determining 64 edge locations in the smoothed image. Projection histograms may be formed 66 from the edge map, and the content boundaries may be detected 68 using the projection histograms. In some embodiments of the present invention, the smoothed version of the input image may be derived 62 by smoothing the input image using a 3×3 Gaussian filter. In alternative embodiments, smoothing may comprise Gaussian filters of other size, smoothing filters of other types and other smoothing techniques known in the art. - In some embodiments of the present invention described in relation to
FIG. 7 , an image may be partitioned 72 into non-overlapping blocks. The block content boundaries may be determined 74 according to embodiments of the present invention described above. The block boundaries may be combined 76 to generate the content boundary for the image. In some of these embodiments, the corners of the content boundaries for each block may be determined 74 and designated Ri=[topi bottomi lefti righti]. The content boundaries, which may be designated by the bounding rectangle corners and denoted R, for the image may be determined 76 from the block boundaries according to: -
R=[max(topi) min(bottomi) min(lefti) max(righti)] - for a coordinate origin in the lower-left of an image, and according to:
-
R=[min(topi) max(bottomi) min(lefti) max(righti)] - for a coordinate origin in the upper-left of an image. In some embodiments of the present invention,
determination 74 of the block content boundaries may be performed in parallel by a plurality of processors. In alternative embodiments, thedetermination 74 of the block content boundaries may be performed serially. - In some embodiments of the present invention described in relation to
FIG. 8 , an image may be partitioned 82 into overlapping blocks. The block content boundaries may be determined 84 according to embodiments of the present invention described above. The block boundaries may be combined 86 to generate the content boundary for the image. In some of these embodiments, the corners of the content boundaries for each block may be determined 84 and designated Ri=[topi bottomi lefti righti]. The content boundaries, which may be designated by the bounding rectangle corners and denoted R, for the image may be determined 86 from the block boundaries according to: -
R=[max(topi) min(bottomi) min(lefti) max(righti)] - for a coordinate origin in the lower-left of an image, and according to:
-
R=[min(topi) max(bottomi) min(lefti) max(righti)] - for a coordinate origin in the upper-left of an image. In some embodiments of the present invention,
determination 84 of the block content boundaries may be performed in parallel by a plurality of processors. In alternative embodiments, thedetermination 84 of the block content boundaries may be performed serially. - In some embodiments of the present invention, the input image may be a color image. In alternative embodiments of the present invention, the input image may be a gray-scale image. In still alternative embodiments of the present invention, the input image may be a binary image.
- In some embodiments of the present invention, the input image may be a luminance image corresponding to a color image. In alternative embodiments of the present invention, the input image may be a binary image corresponding to a color image. In still alternative embodiments of the present invention, the input image may be a binary image corresponding to a gray-scale image.
- In some embodiments of the present invention, an image may be cropped according to the determined content boundaries.
- In some embodiments of the present invention, an image may be simultaneously cropped according to the determined content boundaries and skew corrected.
- The terms and expressions which have been employed in the foregoing specification are used therein as terms of description and not of limitation, and there is no intention in the use of such terms and expressions of excluding equivalence of the features shown and described or portions thereof, it being recognized that the scope of the invention is defined and limited only by the claims which follow.
Claims (26)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/175,386 US9547799B2 (en) | 2008-07-17 | 2008-07-17 | Methods and systems for content-boundary detection |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/175,386 US9547799B2 (en) | 2008-07-17 | 2008-07-17 | Methods and systems for content-boundary detection |
Publications (2)
Publication Number | Publication Date |
---|---|
US20100014774A1 true US20100014774A1 (en) | 2010-01-21 |
US9547799B2 US9547799B2 (en) | 2017-01-17 |
Family
ID=41530360
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US12/175,386 Active 2033-02-28 US9547799B2 (en) | 2008-07-17 | 2008-07-17 | Methods and systems for content-boundary detection |
Country Status (1)
Country | Link |
---|---|
US (1) | US9547799B2 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110142341A1 (en) * | 2009-12-16 | 2011-06-16 | Dolan John E | Methods and Systems for Automatic Content-Boundary Detection |
US20130004071A1 (en) * | 2011-07-01 | 2013-01-03 | Chang Yuh-Lin E | Image signal processor architecture optimized for low-power, processing flexibility, and user experience |
US8554005B1 (en) * | 2009-04-02 | 2013-10-08 | Hewlett-Packard Development Company, L.P. | Digital image enhancement method and system that embolden or thin image features |
WO2022173521A1 (en) * | 2021-02-11 | 2022-08-18 | Hewlett-Packard Development Company, L.P. | Image objects extraction |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10270965B2 (en) | 2015-12-04 | 2019-04-23 | Ebay Inc. | Automatic guided capturing and presentation of images |
JP2018055496A (en) * | 2016-09-29 | 2018-04-05 | 日本電産サンキョー株式会社 | Medium recognition device and medium recognition method |
US10095925B1 (en) | 2017-12-18 | 2018-10-09 | Capital One Services, Llc | Recognizing text in image data |
Citations (50)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5335290A (en) * | 1992-04-06 | 1994-08-02 | Ricoh Corporation | Segmentation of text, picture and lines of a document image |
US5452374A (en) * | 1992-04-06 | 1995-09-19 | Ricoh Corporation | Skew detection and correction of a document image representation |
US5528387A (en) * | 1994-11-23 | 1996-06-18 | Xerox Corporation | Electronic image registration for a scanner |
US5781665A (en) * | 1995-08-28 | 1998-07-14 | Pitney Bowes Inc. | Apparatus and method for cropping an image |
US5825914A (en) * | 1995-07-12 | 1998-10-20 | Matsushita Electric Industrial Co., Ltd. | Component detection method |
US5828776A (en) * | 1994-09-20 | 1998-10-27 | Neopath, Inc. | Apparatus for identification and integration of multiple cell patterns |
US5880858A (en) * | 1997-12-31 | 1999-03-09 | Mustek Systems Inc. | Method of auto-cropping images for scanners |
US5892854A (en) * | 1997-01-21 | 1999-04-06 | Xerox Corporation | Automatic image registration using binary moments |
US5901253A (en) * | 1996-04-04 | 1999-05-04 | Hewlett-Packard Company | Image processing system with image cropping and skew correction |
US5974199A (en) * | 1997-03-31 | 1999-10-26 | Eastman Kodak Company | Method for scanning and detecting multiple photographs and removing edge artifacts |
US5978519A (en) * | 1996-08-06 | 1999-11-02 | Xerox Corporation | Automatic image cropping |
US6011635A (en) * | 1995-12-27 | 2000-01-04 | Minolta Co., Ltd. | Image reading apparatus and method for correcting a read image |
US6043823A (en) * | 1995-07-17 | 2000-03-28 | Kabushiki Kaisha Toshiba | Document processing system which can selectively extract and process regions of a document |
US6178270B1 (en) * | 1997-05-28 | 2001-01-23 | Xerox Corporation | Method and apparatus for selecting text and image data from video images |
US6201901B1 (en) * | 1998-06-01 | 2001-03-13 | Matsushita Electronic Industrial Co., Ltd. | Border-less clock free two-dimensional barcode and method for printing and reading the same |
US6282326B1 (en) * | 1998-12-14 | 2001-08-28 | Eastman Kodak Company | Artifact removal technique for skew corrected images |
US6298157B1 (en) * | 1998-02-27 | 2001-10-02 | Adobe Systems Incorporated | Locating and aligning embedded images |
US6310984B2 (en) * | 1998-04-09 | 2001-10-30 | Hewlett-Packard Company | Image processing system with image cropping and skew correction |
US6360026B1 (en) * | 1998-03-10 | 2002-03-19 | Canon Kabushiki Kaisha | Method for determining a skew angle of a bitmap image and de-skewing and auto-cropping the bitmap image |
US6373590B1 (en) * | 1999-02-04 | 2002-04-16 | Seiko Epson Corporation | Method and apparatus for slant adjustment and photo layout |
US6556721B1 (en) * | 2000-01-07 | 2003-04-29 | Mustek Systems Inc. | Method for image auto-cropping |
US6560376B2 (en) * | 1998-09-11 | 2003-05-06 | Hewlett Packard Development Company, L.P. | Automatic rotation of images for printing |
US6674919B1 (en) * | 1999-09-21 | 2004-01-06 | Matsushita Electric Industrial Co., Ltd. | Method for determining the skew angle of a two-dimensional barcode |
US6901168B1 (en) * | 1998-05-07 | 2005-05-31 | France Telecom | Method for segmenting and identifying a document, in particular a technical chart |
US20050168775A1 (en) * | 2004-01-26 | 2005-08-04 | Liu K. C. | Method and computer program product for in-house digital photo/card processing and printing/cutting production |
US6956587B1 (en) * | 2003-10-30 | 2005-10-18 | Microsoft Corporation | Method of automatically cropping and adjusting scanned images |
US20050244079A1 (en) * | 2004-04-30 | 2005-11-03 | Tsung-Wei Lin | Method for image cropping |
US6973222B2 (en) * | 2000-04-28 | 2005-12-06 | Shutterfly, Inc. | System and method of cropping an image |
US6987880B2 (en) * | 2001-03-22 | 2006-01-17 | Sharp Laboratories Of America, Inc. | Efficient document boundary determination |
US20060072847A1 (en) * | 2004-10-01 | 2006-04-06 | Microsoft Corporation | System for automatic image cropping based on image saliency |
US7034848B2 (en) * | 2001-01-05 | 2006-04-25 | Hewlett-Packard Development Company, L.P. | System and method for automatically cropping graphical images |
US20060098844A1 (en) * | 2004-11-05 | 2006-05-11 | Huitao Luo | Object detection utilizing a rotated version of an image |
US20060109282A1 (en) * | 2004-11-23 | 2006-05-25 | Xiaofan Lin | Non-rectangular image cropping methods and systems |
US7065261B1 (en) * | 1999-03-23 | 2006-06-20 | Minolta Co., Ltd. | Image processing device and image processing method for correction of image distortion |
US7068855B2 (en) * | 2002-07-16 | 2006-06-27 | Hewlett-Packard Development Company, L.P. | System and method for manipulating a skewed digital image |
US20060188173A1 (en) * | 2005-02-23 | 2006-08-24 | Microsoft Corporation | Systems and methods to adjust a source image aspect ratio to match a different target aspect ratio |
US20060228044A1 (en) * | 2005-04-12 | 2006-10-12 | Newsoft Technology Corporation | Method for automatically cropping image objects |
US7133050B2 (en) * | 2003-07-11 | 2006-11-07 | Vista Print Technologies Limited | Automated image resizing and cropping |
US7133571B2 (en) * | 2000-12-22 | 2006-11-07 | Hewlett-Packard Development Company, L.P. | Automated cropping of electronic images |
US20060280364A1 (en) * | 2003-08-07 | 2006-12-14 | Matsushita Electric Industrial Co., Ltd. | Automatic image cropping system and method for use with portable devices equipped with digital cameras |
US20070013974A1 (en) * | 2005-07-11 | 2007-01-18 | Canon Kabushiki Kaisha | Image processing apparatus and its program and control method |
US20070076979A1 (en) * | 2005-10-03 | 2007-04-05 | Microsoft Corporation | Automatically cropping an image |
US7201323B2 (en) * | 2004-12-10 | 2007-04-10 | Mitek Systems, Inc. | System and method for check fraud detection using signature validation |
US7209149B2 (en) * | 2000-06-05 | 2007-04-24 | Fujifilm Corporation | Image cropping and synthesizing method, and imaging apparatus |
US7239726B2 (en) * | 2001-12-12 | 2007-07-03 | Sony Corporation | System and method for effectively extracting facial feature information |
US7305146B2 (en) * | 2001-06-30 | 2007-12-04 | Hewlett-Packard Development Company, L.P. | Tilt correction of electronic images |
US20090180694A1 (en) * | 2008-01-11 | 2009-07-16 | Sharp Laboratories Of America, Inc. | Method and apparatus for determining an orientation of a document including Korean characters |
US7657091B2 (en) * | 2006-03-06 | 2010-02-02 | Mitek Systems, Inc. | Method for automatic removal of text from a signature area |
US7720291B2 (en) * | 2004-02-17 | 2010-05-18 | Corel Corporation | Iterative fisher linear discriminant analysis |
US20110142341A1 (en) * | 2009-12-16 | 2011-06-16 | Dolan John E | Methods and Systems for Automatic Content-Boundary Detection |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4600019B2 (en) | 2004-12-07 | 2010-12-15 | カシオ計算機株式会社 | Imaging apparatus, image processing method, and program |
JP4884305B2 (en) | 2007-06-06 | 2012-02-29 | シャープ株式会社 | Image processing apparatus, image forming apparatus, computer program, and recording medium |
-
2008
- 2008-07-17 US US12/175,386 patent/US9547799B2/en active Active
Patent Citations (55)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5854854A (en) * | 1992-04-06 | 1998-12-29 | Ricoh Corporation | Skew detection and correction of a document image representation |
US5452374A (en) * | 1992-04-06 | 1995-09-19 | Ricoh Corporation | Skew detection and correction of a document image representation |
US5465304A (en) * | 1992-04-06 | 1995-11-07 | Ricoh Corporation | Segmentation of text, picture and lines of a document image |
US5335290A (en) * | 1992-04-06 | 1994-08-02 | Ricoh Corporation | Segmentation of text, picture and lines of a document image |
US5828776A (en) * | 1994-09-20 | 1998-10-27 | Neopath, Inc. | Apparatus for identification and integration of multiple cell patterns |
US5528387A (en) * | 1994-11-23 | 1996-06-18 | Xerox Corporation | Electronic image registration for a scanner |
US5825914A (en) * | 1995-07-12 | 1998-10-20 | Matsushita Electric Industrial Co., Ltd. | Component detection method |
US6043823A (en) * | 1995-07-17 | 2000-03-28 | Kabushiki Kaisha Toshiba | Document processing system which can selectively extract and process regions of a document |
US5781665A (en) * | 1995-08-28 | 1998-07-14 | Pitney Bowes Inc. | Apparatus and method for cropping an image |
US6011635A (en) * | 1995-12-27 | 2000-01-04 | Minolta Co., Ltd. | Image reading apparatus and method for correcting a read image |
US5901253A (en) * | 1996-04-04 | 1999-05-04 | Hewlett-Packard Company | Image processing system with image cropping and skew correction |
US5978519A (en) * | 1996-08-06 | 1999-11-02 | Xerox Corporation | Automatic image cropping |
US5892854A (en) * | 1997-01-21 | 1999-04-06 | Xerox Corporation | Automatic image registration using binary moments |
US5974199A (en) * | 1997-03-31 | 1999-10-26 | Eastman Kodak Company | Method for scanning and detecting multiple photographs and removing edge artifacts |
US6178270B1 (en) * | 1997-05-28 | 2001-01-23 | Xerox Corporation | Method and apparatus for selecting text and image data from video images |
US5880858A (en) * | 1997-12-31 | 1999-03-09 | Mustek Systems Inc. | Method of auto-cropping images for scanners |
US6298157B1 (en) * | 1998-02-27 | 2001-10-02 | Adobe Systems Incorporated | Locating and aligning embedded images |
US6360026B1 (en) * | 1998-03-10 | 2002-03-19 | Canon Kabushiki Kaisha | Method for determining a skew angle of a bitmap image and de-skewing and auto-cropping the bitmap image |
US6430320B1 (en) * | 1998-04-09 | 2002-08-06 | Hewlett-Packard Company | Image processing system with automatic image cropping and skew correction |
US6310984B2 (en) * | 1998-04-09 | 2001-10-30 | Hewlett-Packard Company | Image processing system with image cropping and skew correction |
US6901168B1 (en) * | 1998-05-07 | 2005-05-31 | France Telecom | Method for segmenting and identifying a document, in particular a technical chart |
US20010007116A1 (en) * | 1998-06-01 | 2001-07-05 | Jiangying Zhou | Border-less clock free two-dimensional barcode and method for printing and reading the same |
US20010005867A1 (en) * | 1998-06-01 | 2001-06-28 | Jiangying Zhou | Border-less clock free two-dimensional barcode and method for printing and reading the same |
US6201901B1 (en) * | 1998-06-01 | 2001-03-13 | Matsushita Electronic Industrial Co., Ltd. | Border-less clock free two-dimensional barcode and method for printing and reading the same |
US6560376B2 (en) * | 1998-09-11 | 2003-05-06 | Hewlett Packard Development Company, L.P. | Automatic rotation of images for printing |
US6282326B1 (en) * | 1998-12-14 | 2001-08-28 | Eastman Kodak Company | Artifact removal technique for skew corrected images |
US6373590B1 (en) * | 1999-02-04 | 2002-04-16 | Seiko Epson Corporation | Method and apparatus for slant adjustment and photo layout |
US7065261B1 (en) * | 1999-03-23 | 2006-06-20 | Minolta Co., Ltd. | Image processing device and image processing method for correction of image distortion |
US6674919B1 (en) * | 1999-09-21 | 2004-01-06 | Matsushita Electric Industrial Co., Ltd. | Method for determining the skew angle of a two-dimensional barcode |
US6556721B1 (en) * | 2000-01-07 | 2003-04-29 | Mustek Systems Inc. | Method for image auto-cropping |
US6973222B2 (en) * | 2000-04-28 | 2005-12-06 | Shutterfly, Inc. | System and method of cropping an image |
US7209149B2 (en) * | 2000-06-05 | 2007-04-24 | Fujifilm Corporation | Image cropping and synthesizing method, and imaging apparatus |
US7133571B2 (en) * | 2000-12-22 | 2006-11-07 | Hewlett-Packard Development Company, L.P. | Automated cropping of electronic images |
US7034848B2 (en) * | 2001-01-05 | 2006-04-25 | Hewlett-Packard Development Company, L.P. | System and method for automatically cropping graphical images |
US6987880B2 (en) * | 2001-03-22 | 2006-01-17 | Sharp Laboratories Of America, Inc. | Efficient document boundary determination |
US7305146B2 (en) * | 2001-06-30 | 2007-12-04 | Hewlett-Packard Development Company, L.P. | Tilt correction of electronic images |
US7239726B2 (en) * | 2001-12-12 | 2007-07-03 | Sony Corporation | System and method for effectively extracting facial feature information |
US7068855B2 (en) * | 2002-07-16 | 2006-06-27 | Hewlett-Packard Development Company, L.P. | System and method for manipulating a skewed digital image |
US7133050B2 (en) * | 2003-07-11 | 2006-11-07 | Vista Print Technologies Limited | Automated image resizing and cropping |
US20060280364A1 (en) * | 2003-08-07 | 2006-12-14 | Matsushita Electric Industrial Co., Ltd. | Automatic image cropping system and method for use with portable devices equipped with digital cameras |
US6956587B1 (en) * | 2003-10-30 | 2005-10-18 | Microsoft Corporation | Method of automatically cropping and adjusting scanned images |
US20050168775A1 (en) * | 2004-01-26 | 2005-08-04 | Liu K. C. | Method and computer program product for in-house digital photo/card processing and printing/cutting production |
US7720291B2 (en) * | 2004-02-17 | 2010-05-18 | Corel Corporation | Iterative fisher linear discriminant analysis |
US20050244079A1 (en) * | 2004-04-30 | 2005-11-03 | Tsung-Wei Lin | Method for image cropping |
US20060072847A1 (en) * | 2004-10-01 | 2006-04-06 | Microsoft Corporation | System for automatic image cropping based on image saliency |
US20060098844A1 (en) * | 2004-11-05 | 2006-05-11 | Huitao Luo | Object detection utilizing a rotated version of an image |
US20060109282A1 (en) * | 2004-11-23 | 2006-05-25 | Xiaofan Lin | Non-rectangular image cropping methods and systems |
US7201323B2 (en) * | 2004-12-10 | 2007-04-10 | Mitek Systems, Inc. | System and method for check fraud detection using signature validation |
US20060188173A1 (en) * | 2005-02-23 | 2006-08-24 | Microsoft Corporation | Systems and methods to adjust a source image aspect ratio to match a different target aspect ratio |
US20060228044A1 (en) * | 2005-04-12 | 2006-10-12 | Newsoft Technology Corporation | Method for automatically cropping image objects |
US20070013974A1 (en) * | 2005-07-11 | 2007-01-18 | Canon Kabushiki Kaisha | Image processing apparatus and its program and control method |
US20070076979A1 (en) * | 2005-10-03 | 2007-04-05 | Microsoft Corporation | Automatically cropping an image |
US7657091B2 (en) * | 2006-03-06 | 2010-02-02 | Mitek Systems, Inc. | Method for automatic removal of text from a signature area |
US20090180694A1 (en) * | 2008-01-11 | 2009-07-16 | Sharp Laboratories Of America, Inc. | Method and apparatus for determining an orientation of a document including Korean characters |
US20110142341A1 (en) * | 2009-12-16 | 2011-06-16 | Dolan John E | Methods and Systems for Automatic Content-Boundary Detection |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8554005B1 (en) * | 2009-04-02 | 2013-10-08 | Hewlett-Packard Development Company, L.P. | Digital image enhancement method and system that embolden or thin image features |
US20110142341A1 (en) * | 2009-12-16 | 2011-06-16 | Dolan John E | Methods and Systems for Automatic Content-Boundary Detection |
US8873864B2 (en) * | 2009-12-16 | 2014-10-28 | Sharp Laboratories Of America, Inc. | Methods and systems for automatic content-boundary detection |
US20130004071A1 (en) * | 2011-07-01 | 2013-01-03 | Chang Yuh-Lin E | Image signal processor architecture optimized for low-power, processing flexibility, and user experience |
CN103733189A (en) * | 2011-07-01 | 2014-04-16 | 英特尔公司 | Image signal processor architecture optimized for low-power, processing flexibility, and user experience |
WO2022173521A1 (en) * | 2021-02-11 | 2022-08-18 | Hewlett-Packard Development Company, L.P. | Image objects extraction |
Also Published As
Publication number | Publication date |
---|---|
US9547799B2 (en) | 2017-01-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9547799B2 (en) | Methods and systems for content-boundary detection | |
US8873864B2 (en) | Methods and systems for automatic content-boundary detection | |
US8290265B2 (en) | Method and apparatus for segmenting an object region of interest from an image | |
US6400848B1 (en) | Method for modifying the perspective of a digital image | |
US9122921B2 (en) | Method for detecting a document boundary | |
US9390342B2 (en) | Methods, systems and apparatus for correcting perspective distortion in a document image | |
US8755563B2 (en) | Target detecting method and apparatus | |
US20160314563A1 (en) | Method for correcting fragmentary or deformed quadrangular image | |
US20120294528A1 (en) | Method of Detecting and Correcting Digital Images of Books in the Book Spine Area | |
US20140064623A1 (en) | Image feature extraction apparatus and image feature extraction method, and image processing system using the same | |
US8620080B2 (en) | Methods and systems for locating text in a digital image | |
US8265416B2 (en) | Method, apparatus and integrated circuit for improving image sharpness | |
US8520953B2 (en) | Apparatus and method for extracting edges of image | |
US9111165B2 (en) | Method and system for filtering detection patterns in a QR code | |
WO2016197571A1 (en) | Image interpolation device and method thereof | |
US20160259990A1 (en) | Region-of-interest detection apparatus, region-of-interest detection method, and recording medium | |
KR101822909B1 (en) | Method and device for detecting elliptical structure in an image | |
US20120320433A1 (en) | Image processing method, image processing device and scanner | |
US8275170B2 (en) | Apparatus and method for detecting horizon in sea image | |
US9378405B2 (en) | Determining barcode locations in documents | |
JP3659426B2 (en) | Edge detection method and edge detection apparatus | |
CN113298787A (en) | Plate edge sealing defect detection method, controller and computer readable storage medium | |
Fang et al. | 1-D barcode localization in complex background | |
US20140147056A1 (en) | Depth image noise removal apparatus and method based on camera pose | |
US11134170B2 (en) | Correction of feed skewed images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: SHARP LABORATORIES OF AMERICA, INC.,WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CHEN, LAWRENCE SHAO-HSIEN;DOLAN, JOHN E.;REEL/FRAME:021255/0874 Effective date: 20080715 Owner name: SHARP LABORATORIES OF AMERICA, INC., WASHINGTON Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:CHEN, LAWRENCE SHAO-HSIEN;DOLAN, JOHN E.;REEL/FRAME:021255/0874 Effective date: 20080715 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
AS | Assignment |
Owner name: SHARP KABUSHIKI KAISHA, JAPAN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:SHARP LABORATORIES OF AMERICA, INC.;REEL/FRAME:041024/0183 Effective date: 20170120 |
|
MAFP | Maintenance fee payment |
Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Year of fee payment: 4 |